Digital Twin Model-Driven Eccentricity Fault Quantitative Diagnosis of Permanent Magnet Synchronous Motors

doi:10.3901/JME.260743

Abstract

Abstract: Eccentricity fault is a common type of failure in permanent magnet synchronous motors, which causes fluctuations in the internal magnetic field and current signals. Based on an improved winding function approach, a high-fidelity simulation-enhanced model considering actual air-gap distribution is established to reveal the electromechanical coupling mechanism. To address the lack of fault samples under multiple eccentricity levels, a quantitative diagnosis method driven by high-fidelity simulation and transfer learning is proposed. Specifically, fault samples are generated using the simulation model, transfer learning aligns features between the source domain (simulation data) and target domain (experimental data), and margin-aware regularization enhances fault recognition under imbalanced conditions. Finally, experiments on a dedicated test bench demonstrate that when fault samples account for only 4.8% of the total, the proposed method achieves an average diagnostic accuracy of 92.5%, significantly improving accuracy and robustness.

Key words: permanent magnet synchronous motor, digital twin, fault diagnosis, transfer learning

CLC Number:

TH17

LI Naipeng, ZHANG Tao, LEI Yaguo, LI Xiang, YANG Bin, JIANG Jinze. Digital Twin Model-Driven Eccentricity Fault Quantitative Diagnosis of Permanent Magnet Synchronous Motors[J]. Journal of Mechanical Engineering, 2026, 62(14): 59-71.

Add to citation manager EndNote|Reference Manager|ProCite|BibTeX|RefWorks

URL: http://www.cjmenet.com.cn/EN/10.3901/JME.260743

http://www.cjmenet.com.cn/EN/Y2026/V62/I14/59

References

[1] 唐任远. 现代永磁电机理论与设计[M]. 北京：机械工业出版社，2008. TANG Renyuan. Modern theory and design of permanent magnet machines[M]. Beijing：China Machine Press，2008.
[2] CAO Wenping，MEROW B C，ATKINSON G J，et al. Overview of electric motor technologies used for more electric aircraft(MEA)[J]. IEEE Transactions on Industrial Electronics，2012，59(9)：3523-3531.
[3] ZAFARANI M，BOSTANCI E，QI Yuan，et al. Interturn short-circuit faults in permanent magnet synchronous machines：An extended review and comprehensive analysis[J]. IEEE Journal of Emerging and Selected Topics in Power Electronics，2018，6(4)：2173-2191.
[4] ZHU Zongqin，HOWE D. Electrical machines and drives for electric，hybrid，and fuel cell vehicles[J]. Proceedings of the IEEE，2007，95(4)：746-765.
[5] EBRAHIMI B M，FAIZ J，ROSHTKHARI M J. Static-，dynamic-，and mixed-eccentricity fault diagnoses in permanent-magnet synchronous motors[J]. IEEE Transactions on Industrial Electronics，2009，56(11)：4727-4739.
[6] HONG J，PARK S，HYUN D，et al. Detection and classification of rotor demagnetization and eccentricity faults for PM synchronous motors[J]. IEEE Transactions on Industry Applications，2012，48(3)：923-932.
[7] BARHOUR A，THOMEON W T. Finite element study of rotor slot designs with respect to current monitoring for detecting static airgap eccentricity in squirrel-cage induction motors[C]//Conference Record of the 1997 IEEE Industry Applications Conference - Thirty-Second IAS Annual Meeting (IAS '97)，Vols 1-3，IEEE，1997. 1997：112-119.
[8] DI Chong，BAO Xiaohua，WANG Hanfeng，et al. Modeling and analysis of unbalanced magnetic pull in cage induction motors with curved dynamic eccentricity[J]. IEEE Transactions on Magnetics，2015，51(8)：1-7.
[9] CHEN Yong，LIANG Siyuan，LI Wanfu，et al. Faults and diagnosis methods of permanent magnet synchronous motors：A review[J]. Applied Sciences-Basel，2019，9(10)：2116.
[10] CHOI S，HAQUE M S，BIN Tarek M T，et al. Fault diagnosis techniques for permanent magnet AC machine and drives-A review of current state of the art[J]. IEEE Transactions on Industrial Electronics，2018，4(2)：444-463.
[11] HAN Qinkai，JIANG Ziyuan，KONG Yun，et al. Motor current model for detecting localized defects in planet rolling bearings[J]. IEEE Transactions on Industrial Electronics，2023，70(9)：9483-94.
[12] KLEIN C，PINTER M，PALMIERI M，et al. An exact solution to the modified winding function for eccentric permanent magnet synchronous machines[J]. Mathematics，2022，10(3)：345.
[13] RAFAQ M S，LEE H，PARK Y，et al. A simple method for identifying mass unbalance using vibration measurement in permanent magnet synchronous motors[J]. IEEE Transactions on Industrial Electronics，2022，69(6)：6441-6444.
[14] WANG Yuchen，LIU Kai，HUA Wei，et al. Analysis and detection of rotor eccentricity in permanent magnet synchronous machines based on linear hall sensors[J]. IEEE Transactions on Power Electronics，2022，37(4)：4719-4729.
[15] CHEN Xiaowang，FENG Zhiping. Induction motor stator current analysis for planetary gearbox fault diagnosis under time-varying speed conditions[J]. Mechanical Systems and Signal Processing，2020，140：106691.
[16] ZHOU Shengsen，MA Conggan，WANG Yanyan，et al. A new data-driven diagnosis method for mixed eccentricity in external rotor permanent magnet motors[J]. IEEE Transactions on Industrial Electronics，2023，70(11)：11659-11669.
[17] LIN Cuiying，KONG Yun，HUAN Guoyu，et al. Generalization classification regularization generative adversarial network for machinery fault diagnostics under data imbalance[J]. Reliability Engineering and System Safety，2025，256：110791.
[18] 雷亚国，杨彬，李乃鹏，等. 跨设备的机械故障靶向迁移诊断方法[J]. 机械工程学报，2022，58(12)：1-9. LEI Yaguo，YANG Bin，LI Naipeng，et al. Targeted transfer diagnosis method across different machines[J]. Journal of Mechanical Engineering，2022，58(12)：1-9.
[19] 马帅，冷杰武，陈祝云，等. 基于数字孪生和深度迁移学习的电主轴热误差建模方法[J]. 机械工程学报，2025，61(3)：52-66. MA Shuai，LENG Jiewu，CHEN Zhuyun，et al. Thermal error modeling method for motorized spindles based on digital twin and deep transfer learning[J]. Journal of Mechanical Engineering，2025，61(3)：52-66.
[20] SONG Wensheng，ZOU Yuchao，MA Chenwei，et al. Digital twin modeling method of three-phase inverter-driven PMSM systems for parameter estimation[J]. IEEE Transactions on Power Electronics，2024，39(2)：2360-2371.
[21] XIA Pengcheng，HUANG Yixiang，TAO Zhiyu，et al. A digital twin-enhanced semi-supervised framework for motor fault diagnosis based on phase-contrastive current dot pattern[J]. Reliability Engineering and System Safety，2023，235：109256.
[22] CHEN Zhichao，LIANG Deliang，JIA Shaofeng，et al. Incipient interturn short-circuit fault diagnosis of permanent magnet synchronous motors based on the data-driven digital twin model[J]. IEEE Journal of Emerging and Selected Topics in Power Electronics，2023，11(3)：3514-3524.
[23] YAN Shen，ZHONG Xiang，SHAO Haidong，et al. Digital twin-assisted imbalanced fault diagnosis framework using subdomain adaptive mechanism and margin-aware regularization[J]. Reliability Engineering and System Safety，2023，239：109522.
[24] CUI Yin，JIA Menglin，LIN T-Y，et al. Class-balanced loss based on effective number of samples[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2019). 2019：9260-9.10.1109/ CVPR.2019.00949
[25] FERNANDO K R M，TSOKOS C P. Dynamically weighted balanced loss：Class imbalanced learning and confidence calibration of deep neural networks[J]. IEEE Transactions on neural networks and learning systems，2022，33(7)：2940-2951.
[26] LI Wei，ZHONG Xiang，SHAO Haidong，et al. Multi-mode data augmentation and fault diagnosis of rotating machinery using modified ACGAN designed with new framework[J]. Advanced Engineering Informatics，2022，52：101552.
[27] LIU Shaowei，JIANG Hongkai，WU Zhenghong，et al. Rolling bearing fault diagnosis using variational autoencoding generative adversarial networks with deep regret analysis[J]. Measurement，2021，168：108371.